© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 62781
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rapy
    -0.26
    _plate
    -0.25
     Grave
    -0.25
     zaj
    -0.24
     Knife
    -0.23
    repeat
    -0.23
    edia
    -0.23
    亡
    -0.23
    andum
    -0.23
    rim
    -0.22
    POSITIVE LOGITS
    è£Ĥ
    0.26
    åĵº
    0.25
    èµ°è¿ĩ
    0.25
     análise
    0.25
    Vectorizer
    0.24
    æ£ł
    0.24
    unlikely
    0.24
    ctxt
    0.23
    æ¥ł
    0.23
     anál
    0.23
    Activations Density 54.748%

    No Known Activations

    This feature has no known activations.